{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3NW764V4H5AAI2KRXSB5VXYMMR","short_pith_number":"pith:3NW764V4","schema_version":"1.0","canonical_sha256":"db6dff72bc3f40046951bc83dadf0c644b138bf2f609e556df1086fcb9f2d34d","source":{"kind":"arxiv","id":"2606.06011","version":1},"attestation_state":"computed","paper":{"title":"Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Christian Llanes, Samuel Coogan, Spencer W. Jensen","submitted_at":"2026-06-04T11:01:00Z","abstract_excerpt":"In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasible actions in cooperative multi-agent tasks. Multi-agent reinforcement learning provides the advantage of learning cooperative policies for multi-agent teams from discrete non-differentiable rewards in a long planning horizon. Model-predictive control is robust and offers safe, dynamically feasible actions in a fast replanning framework for short horizons. We propose an algorithm that extends actor-critic model predictive control for MARL whic"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.06011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T11:01:00Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"fba7f1bc8ce432e02e2714a001c3e8dc49026f5c19c0ff4d23b297b4d1e51b7a","abstract_canon_sha256":"8ee680adc5f60ba14b5373bebbbdc1364c94010257d226401a36e0b3671a43fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:30.303635Z","signature_b64":"0ZVAYaQ8M/nZjuob5WZNtbA0arn3GWfd+XPHH+URd4AdD8rBxmllec9mZwSx51bQZl65Eu8QI+8fG3WfCgseAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db6dff72bc3f40046951bc83dadf0c644b138bf2f609e556df1086fcb9f2d34d","last_reissued_at":"2026-06-05T01:15:30.303176Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:30.303176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Christian Llanes, Samuel Coogan, Spencer W. Jensen","submitted_at":"2026-06-04T11:01:00Z","abstract_excerpt":"In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasible actions in cooperative multi-agent tasks. Multi-agent reinforcement learning provides the advantage of learning cooperative policies for multi-agent teams from discrete non-differentiable rewards in a long planning horizon. Model-predictive control is robust and offers safe, dynamically feasible actions in a fast replanning framework for short horizons. We propose an algorithm that extends actor-critic model predictive control for MARL whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06011","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.06011/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.06011","created_at":"2026-06-05T01:15:30.303232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06011v1","created_at":"2026-06-05T01:15:30.303232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06011","created_at":"2026-06-05T01:15:30.303232+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NW764V4H5AA","created_at":"2026-06-05T01:15:30.303232+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NW764V4H5AAI2KR","created_at":"2026-06-05T01:15:30.303232+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NW764V4","created_at":"2026-06-05T01:15:30.303232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR","json":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR.json","graph_json":"https://pith.science/api/pith-number/3NW764V4H5AAI2KRXSB5VXYMMR/graph.json","events_json":"https://pith.science/api/pith-number/3NW764V4H5AAI2KRXSB5VXYMMR/events.json","paper":"https://pith.science/paper/3NW764V4"},"agent_actions":{"view_html":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR","download_json":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR.json","view_paper":"https://pith.science/paper/3NW764V4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06011&json=true","fetch_graph":"https://pith.science/api/pith-number/3NW764V4H5AAI2KRXSB5VXYMMR/graph.json","fetch_events":"https://pith.science/api/pith-number/3NW764V4H5AAI2KRXSB5VXYMMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR/action/storage_attestation","attest_author":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR/action/author_attestation","sign_citation":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR/action/citation_signature","submit_replication":"https://pith.science/pith/3NW764V4H5AAI2KRXSB5VXYMMR/action/replication_record"}},"created_at":"2026-06-05T01:15:30.303232+00:00","updated_at":"2026-06-05T01:15:30.303232+00:00"}